X gamma ray real-time discrimination system based on energy spectrum-space-time fusion

Abstract

The invention belongs to the technical field of radiation detection and analysis, and particularly relates to Xamp based on energy spectrum-space-time fusion. The gamma ray real-time discrimination system comprises a double-layer detector which comprises an upper filtering layer and a lower full spectrum layer and is used for receiving and discriminating X rays and gamma rays; the data acquisition module is used for synchronously acquiring energy spectrum, time sequence pulse and spatial distribution data; according to the time sequence analysis and LSTM network, LSTM serves as a special recurrent neural network, has remarkable advantages in the aspects of processing long sequence data and capturing a long-term dependency relationship, and can make up for the defects of a traditional time sequence analysis method; the feature extraction module is a bridge for connecting original data and a prediction model in time sequence analysis, and is used for calculating a K-edge peak area proportion and outputting a judgment effective pulse according to an LSTM network; by combining the double-layer detector with the LSTM network, 300ms-level real-time response is realized, the capability of distinguishing X-rays and gamma-rays is improved, and the accuracy and reliability of overall detection are also enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of radiation detection and analysis, and in particular is an X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion. Background Art

[0002] X-ray security inspection equipment may leak X-rays due to shielding failure or mechanical wear during operation. The energy range of X-rays (1-150keV) significantly overlaps with the gamma rays (10keV-3MeV) released by natural radioactive substances in the environment (such as 137Cs and 226Ra). Traditional methods rely on a single energy threshold or pulse width detection, with a misjudgment rate of up to 30%-40%, resulting in frequent false alarms in the radiation safety monitoring system, affecting the normal operation of the equipment.

[0003] In addition, X-ray leakage has directional and pulsed characteristics, while gamma rays are isotropic and continuous radiation. It is difficult to distinguish the two through a single parameter in a mixed radiation field. Existing detection technologies, such as the energy spectrum threshold method, can distinguish X-rays and gamma rays by setting a fixed energy threshold (such as 50 keV). However, low-energy gamma rays (such as 59.5 keV of 241Am) overlap with the K-edge characteristic peak of X-rays (20-80 keV), leading to misjudgment. If the time filtering method is used to make a distinction based on the difference between the X-ray pulse width (10-100 μs) and the continuous radiation of gamma rays, the response time of commonly used scintillator detectors is >100 ns, making it difficult to distinguish the difference between the two in an extremely short time.

[0004] Therefore, to address the above problems, a real-time X&γ-ray identification system based on energy spectrum-time-space fusion is proposed. Summary of the Invention

[0005] (1) Technical problems solved

[0006] In view of the shortcomings of the existing technology, the present invention provides an X & γ ray real-time identification system based on energy spectrum-time-space fusion, which is used to solve the problems raised in the background technology.

[0007] (2) Technical solution

[0008] To achieve the above objectives, the present invention provides the following technical solution: a real-time X-ray and gamma-ray identification system based on energy spectrum-time-space fusion, the system comprising:

[0009] Double-layer detector: It consists of an upper filter layer and a lower full-spectrum layer, used to receive and distinguish X-rays and gamma rays;

[0010] Data acquisition module: synchronously acquires energy spectrum, time-series pulse and spatial distribution data, and ensures data synchronization through time stamp technology;

[0011] Time series analysis and LSTM networks: As a special type of recurrent neural network, LSTM has significant advantages in processing long sequence data and capturing long-term dependencies, which can offset the shortcomings of traditional time series analysis methods.

[0012] Feature extraction module: It is the bridge connecting the original data and the prediction model in time series analysis. It is used to calculate the K-edge peak area ratio and determine the effective pulse based on the LSTM network output;

[0013] Fusion decision module: Based on the dynamic weighted fusion model, it makes a comprehensive judgment by combining the energy spectrum weight, peak area ratio, time series weight and time series matching degree to trigger the X-ray leakage alarm.

[0014] Preferably, the upper filter layer uses 0.2mm copper foil to shield X-rays with energy <20keV, retaining the K-edge characteristic peak of 20-80keV and reducing interference from low-energy gamma rays;

[0015] Lower full spectrum layer: The SiPM array coupled NaI crystal size is φ~50mm×50mm, covering the 1-300keV energy range. The formula for inverting the leakage X-ray energy spectrum is:

[0016] ΔN(E)=N full (E)-N filter (E);

[0017] In the above formula: N full (E) is the full energy spectrum, N filter (E) is the energy spectrum of the filter layer E∈[20,80]keV.

[0018] The upper filter layer directly affects the energy resolution and imaging quality of the detector. Through unique material and structural design, it achieves the synchronous acquisition of full-energy spectral information, provides multi-dimensional material quantitative analysis capabilities for clinical diagnosis, and enhances detection resolution.

[0019] Preferably, the data acquisition module acquires raw data from the double-layer detector in real time according to a set acquisition frequency, and ensures data synchronization through a timestamp technology. At the same time, the acquired data is preliminarily processed to improve data quality.

[0020] Preferably, the calculation formula for the K-edge peak area ratio is:

[0021]

[0022] Preferably, the timing analysis and LSTM network include:

[0023] Signal synchronization: The high-voltage power supply signal of the X-ray machine is collected as H(t), the detector pulse is D(t), and the cross-correlation function is constructed:

[0024]

[0025] LSTM network: The input layer is R with a 100-point time window H D(τ) sequence, hidden layer 32 nodes, output time series matching degree T(t)∈[0,1], captures the causal relationship between X-ray pulses and device power on and off;

[0026] LSTM outputs T(t), and the threshold T(t)>0.7 is judged as a valid pulse.

[0027] Preferably, the dynamic weighted fusion model performs comprehensive calculations based on the energy spectrum weight, peak area ratio, timing weight and timing matching to obtain the identification results; establishes weight adaptive rules, and dynamically adjusts the weight according to the environmental background γ dose rate and the equipment operating frequency to ensure that the energy spectrum weight is improved in a high background environment and the timing weight is improved in a pulse-intensive scenario.

[0028] Preferably, the criterion formula of the dynamic weighted fusion model is:

[0029] P x =α·S(E)+β·T(t)+ε cal ;

[0030] In the above formula, α is the energy spectrum weight; S(E) is the peak area ratio; β is the time series weight; T(t) is the time series matching degree; ε cal Calibration factor: Dynamically compensates for detector gain drift based on the temperature sensor to ensure an error of <3% under -30℃ ~ 60℃ working conditions.

[0031] Based on the above model, the following weight adaptive rules are established:

[0032] In high background environments, with a gamma dose rate > 1μSv / h: increase the energy spectrum weight α to 0.5 to suppress temporal interference;

[0033] In pulse-intensive scenarios with device frequency > 100 Hz, increase the timing weight β to 0.4 to enhance short pulse recognition.

[0034] Preferably, the threshold value P of the criterion formula of the dynamic weighted fusion model is x ≥0.8 triggers the X-ray leakage alarm.

[0035] Experimental steps:

[0036] The system detector was placed 1 meter from the gamma radiation source's beam exit at the X-ray machine's exit. Tests were conducted with the X-ray machine and gamma radiation sources of varying energies operating independently, as well as with both operating simultaneously. Simulated temperature and humidity changes (-30°C to 60°C) were also conducted, with each temperature increasing by 5°C. This test was repeated 400 times to verify the system's performance.

[0037] Experimental data:

[0038] The experimental data obtained through the above experiment are shown in the following table:

[0039] Table 1 Comparison data under different working conditions

[0040]

[0041]

[0042] Experimental conclusion:

[0043] The real-time identification system for X-ray leakage and gamma rays based on the fusion of energy spectrum and spatiotemporal features shows significant advantages in complex radiation fields, especially in the overlapping area of low-energy gamma rays and X-rays and under dynamic working conditions. The false alarm rate is reduced by 41% and the response speed is increased by 32%, meeting the needs of industrial-grade real-time monitoring.

[0044] Beneficial effects

[0045] Compared with the existing technology, the present invention provides a real-time X-ray and gamma-ray identification system based on energy spectrum-time-space fusion, which has the following beneficial effects:

[0046] 1. This invention, by combining a double-layer detector with an LSTM network, achieves a real-time response of 300ms, improves the ability to distinguish between X-rays and gamma rays, and enhances the accuracy and reliability of overall detection.

[0047] 2. This invention, through unique material and structural design, enables the system to synchronously collect full-energy spectral information, providing multi-dimensional material quantitative analysis capabilities for clinical diagnosis, and further improving detection resolution and imaging quality.

[0048] 3. This invention overcomes the high misjudgment rate problem caused by traditional methods relying on a single energy threshold or pulse width detection by integrating the energy spectrum K-edge characteristics, device timing synchronization and spatial directionality index.

[0049] 4. This invention introduces a dynamic weighted fusion model to dynamically adjust the weights according to the environmental background gamma dose rate and the equipment operating frequency. This feature ensures the stability and adaptability of the system under different working conditions, especially improving the energy spectrum weight in high-background environments and enhancing the short pulse recognition capability in pulse-intensive scenarios, effectively reducing the false alarm rate and improving the timeliness of the alarm.

[0050] 5. This invention establishes a weighted adaptive rule, and the temperature sensor dynamically compensates for the detector gain drift, ensuring that the error is less than 3% under extreme temperature conditions, thereby ensuring the long-term stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0052] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0054] Specific examples are given below.

[0055] Example

[0056] like Figure 1 As shown, a real-time X-ray and gamma-ray identification system based on energy spectrum-time-space fusion is provided; the specific implementation is as follows:

[0057] Double-layer detector: It consists of an upper filter layer and a lower full-spectrum layer, used to receive and distinguish X-rays and gamma rays;

[0058] Data acquisition module: synchronously acquires energy spectrum, time-series pulse and spatial distribution data, and ensures data synchronization through time stamp technology;

[0059] Time series analysis and LSTM networks: As a special type of recurrent neural network, LSTM has significant advantages in processing long sequence data and capturing long-term dependencies, which can offset the shortcomings of traditional time series analysis methods.

[0060] Feature extraction module: It is the bridge connecting the original data and the prediction model in time series analysis. It is used to calculate the K-edge peak area ratio and determine the effective pulse based on the LSTM network output;

[0061] Fusion decision module: Based on the dynamic weighted fusion model, it makes a comprehensive judgment by combining the energy spectrum weight, peak area ratio, time series weight and time series matching degree to trigger the X-ray leakage alarm.

[0062] The upper filter layer uses 0.2mm copper foil to shield X-rays with energy <20keV, retaining the K-edge characteristic peak 20-80keV and reducing low-energy gamma ray interference;

[0063] Lower full spectrum layer: The SiPM array coupled NaI crystal size is φ~50mm×50mm, covering the 1-300keV energy range. The formula for inverting the leakage X-ray energy spectrum is:

[0064] ΔN(E)=N full (E)-N filter (E);

[0065] In the above formula: N full (E) is the full energy spectrum, N filter (E) is the energy spectrum of the filter layer E∈[20,80]keV.

[0066] The upper filter layer directly affects the energy resolution and imaging quality of the detector. Through unique material and structural design, it achieves the simultaneous acquisition of full-energy spectral information, providing multi-dimensional material quantitative analysis capabilities for clinical diagnosis and enhancing detection resolution.

[0067] Through unique material and structural design, the system can synchronously collect full-energy spectral information, providing multi-dimensional material quantitative analysis capabilities for clinical diagnosis, and further improving detection resolution and imaging quality.

[0068] The data acquisition module acquires raw data from the double-layer detector in real time according to the set acquisition frequency, and ensures the synchronization of the data through the time stamp technology. At the same time, the collected data is preliminarily processed to improve the data quality;

[0069] The calculation formula of the K-edge peak area ratio is:

[0070]

[0071] The timing analysis and LSTM network include:

[0072] Signal synchronization: The high-voltage power supply signal of the X-ray machine is collected as H(t), the detector pulse is D(t), and the cross-correlation function is constructed:

[0073]

[0074] LSTM network: The input layer is R with a 100-point time window H D(τ) sequence, hidden layer 32 nodes, output time series matching degree T(t)∈[0,1], captures the causal relationship between X-ray pulses and device power on and off;

[0075] LSTM output T(t), threshold T(t)>0.7 is judged as a valid pulse;

[0076] By combining a double-layer detector with an LSTM network, a real-time response of 300ms is achieved, which improves the ability to distinguish between X-rays and gamma rays and enhances the accuracy and reliability of overall detection.

[0077] The dynamic weighted fusion model performs comprehensive calculations based on the energy spectrum weight, peak area ratio, timing weight, and timing matching to obtain the identification results. It also establishes a weight adaptive rule to dynamically adjust the weight according to the ambient background gamma dose rate and the equipment operating frequency, ensuring that the energy spectrum weight is increased in high-background environments and the timing weight is increased in pulse-intensive scenarios.

[0078] The criterion formula of the dynamic weighted fusion model is:

[0079] P x =α·S(E)+β·T(t)+ε cal ;

[0080] In the above formula, α is the energy spectrum weight; S(E) is the peak area ratio; β is the time series weight; T(t) is the time series matching degree; ε cal Calibration factor: Dynamically compensates for detector gain drift based on the temperature sensor to ensure an error of <3% under -30℃ ~ 60℃ working conditions.

[0081] Based on the above model, the following weight adaptive rules are established:

[0082] In high background environments, with a gamma dose rate > 1μSv / h: increase the energy spectrum weight α to 0.5 to suppress temporal interference;

[0083] In pulse-intensive scenarios with device frequency > 100 Hz: increase the timing weight β to 0.4 to enhance short pulse recognition.

[0084] By establishing weight adaptation rules, the temperature sensor dynamically compensates for detector gain drift, ensuring that the error is less than 3% under extreme temperature conditions, thereby ensuring the long-term stable operation of the system.

[0085] The threshold value P of the criterion formula of the dynamic weighted fusion model is x ≥0.8 triggers X-ray leakage alarm;

[0086] By introducing a dynamic weighted fusion model, the weights are dynamically adjusted according to the environmental background gamma dose rate and the equipment operating frequency. This feature ensures the stability and adaptability of the system under different working conditions, especially by improving the energy spectrum weight in high-background environments and enhancing the short pulse recognition capability in pulse-intensive scenarios, effectively reducing the false alarm rate and improving the timeliness of alarms.

[0087] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention as claimed.

Claims

1. A real-time X-ray and gamma-ray identification system based on energy spectrum-time-space fusion, characterized in that: The system comprises: Double-layer detector: It consists of an upper filter layer and a lower full-spectrum layer, used to receive and distinguish X-rays and gamma rays; Data acquisition module: synchronously acquires energy spectrum, time-series pulse and spatial distribution data, and ensures data synchronization through time stamp technology; Time series analysis and LSTM networks: As a special type of recurrent neural network, LSTM has significant advantages in processing long sequence data and capturing long-term dependencies, which can offset the shortcomings of traditional time series analysis methods. Feature extraction module: It is the bridge connecting the original data and the prediction model in time series analysis. It is used to calculate the K-edge peak area ratio and determine the effective pulse based on the LSTM network output; Fusion decision module: Based on the dynamic weighted fusion model, it makes a comprehensive judgment by combining the energy spectrum weight, peak area ratio, time series weight and time series matching degree to trigger the X-ray leakage alarm.

2. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 1, characterized in that: The upper filter layer uses 0.2mm copper foil to shield X-rays with energy <20keV, retaining the K-edge characteristic peak 20-80keV and reducing low-energy gamma ray interference; Lower full spectrum layer: The SiPM array coupled NaI crystal size is φ~50mm×50mm, covering the 1-300keV energy range. The formula for inverting the leakage X-ray energy spectrum is: ΔN(E)=N full (ONE filter (E); In the above formula: N full (E) is the full energy spectrum, N filter (E) is the energy spectrum of the filter layer E∈[20,80]keV.

3. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 1, characterized in that: The data acquisition module acquires raw data from the double-layer detector in real time according to the set acquisition frequency, and ensures the synchronization of the data through the time stamp technology. At the same time, the collected data is preliminarily processed to improve the data quality.

4. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 1, characterized in that: The calculation formula of the K-edge peak area ratio is:

5. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 1, characterized in that: The time series analysis and LSTM network include: Signal synchronization: The high-voltage power supply signal of the X-ray machine is collected as H(t), the detector pulse is D(t), and the cross-correlation function is constructed: LSTM network: The input layer is R with a 100-point time window H D(τ) sequence, hidden layer 32 nodes, output time series matching degree T(t)∈[0,1], captures the causal relationship between X-ray pulses and device power on and off; LSTM outputs T(t), and the threshold T(t)>0.7 is judged as a valid pulse.

6. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 1, characterized in that: The dynamic weighted fusion model performs comprehensive calculations based on the energy spectrum weight, peak area ratio, timing weight and timing matching to obtain the identification results; establishes weight adaptive rules to dynamically adjust the weight according to the environmental background γ dose rate and the equipment operating frequency, ensuring that the energy spectrum weight is improved in high background environments and the timing weight is improved in pulse-intensive scenarios.

7. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 5, characterized in that: The criterion formula of the dynamic weighted fusion model is: P x =α·S(E)+β·T(t)+ε cal ; In the above formula, α is the energy spectrum weight; S(E) is the peak area ratio; β is the time series weight; T(t) is the time series matching degree; ε cal Calibration factor: Dynamically compensates for detector gain drift based on the temperature sensor to ensure an error of <3% under -30℃ ~ 60℃ working conditions. Based on the above model, the following weight adaptive rules are established: In high background environments, with a gamma dose rate > 1μSv / h: increase the energy spectrum weight α to 0.5 to suppress temporal interference; In pulse-intensive scenarios with device frequency > 100 Hz, increase the timing weight β to 0.4 to enhance short pulse recognition.

8. The X-ray and gamma-ray real-time identification system based on energy spectrum-time-space fusion according to claim 7, characterized in that: The threshold value P of the criterion formula of the dynamic weighted fusion model is x ≥0.8 triggers the X-ray leakage alarm.

Images